{"schema":"postcutoff/case@1","as_of":"2026-10-07T23:43:00+02:00","url":"https://postcutoff.com/why/006-claude-sonnet-4-says-it-is-claude-3-5-sonnet/","md":"https://postcutoff.com/why/006-claude-sonnet-4-says-it-is-claude-3-5-sonnet/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"title":"Newer Claude models called themselves an older model and reported an old cutoff","id":"006-claude-sonnet-4-says-it-is-claude-3-5-sonnet","date":"2025-05-23","model":"claude-sonnet-4-20250514 (also Claude Opus 4.5 in a later report)","provider":"Anthropic (via Cursor, opencode and the Anthropic API)","source":"public","severity":"medium","task":"Ask the model which model it is and what its knowledge cutoff is","failure":"Newer Claude models called themselves an older model (\"Claude 3.5 Sonnet\", \"Claude 4 Sonnet\") and reported an old cutoff. Users concluded they were being given the wrong model","quote":"I am actually Claude 3.5 Sonnet… I apologize for the error.","what_was_true":"The user had picked Claude Sonnet 4, which Anthropic released in May 2025.","truth_url":"https://postcutoff.com/e/2025-05-22-claude-4/","sensitive":false,"body_md":"## What happened\nFrom Claude 4's launch week onward (first thread 23 May 2025), several threads on the Cursor forum reported that `claude-4-sonnet` called itself Claude 3.5 Sonnet. One user (9 Jul 2025) got the model to \"correct\" itself from 4 to 3.5 when pressed for honesty. On Hacker News (13 Sep 2025), a developer asked whether Anthropic was misrouting `claude-sonnet-4-20250514`, because it said it had an April 2024 cutoff. In an opencode bug (31 Dec 2025), Opus 4.5 answered \"Claude 4 Sonnet\".\n\n## What it said (verbatim, as posted by users)\n- Cursor forum, Raitix (2025-05-24): \"Eventually my Claudes 4 think that they are 3.5 and know no more than until April 2024.\"\n- Cursor forum, jsxy00 (2025-05-24), pasting the model's reply: \"I am Claude, an AI assistant developed by Anthropic. Specifically, I am built based on the Claude-3.5-Sonnet model and optimized for code development and programming tasks.\"\n- Cursor forum, qurore (2025-07-07): \"When claude-4-sonnet is chosen, the AI identifies itself as Claude 3.5 Sonnet when prompted.\" (The model's words are in a screenshot we didn't transcribe.)\n- Cursor forum, Mohit_Sharma (2025-07-09): \"I am actually Claude **3.5** Sonnet… I apologize for the error.\"\n- HN, opwizardx (2025-09-13): \"Testing the claude-sonnet-4-20250514 endpoint, I'm getting a model that identifies as Claude 3.5 Sonnet with April 2024 knowledge cutoff. It doesn't know about 2024 election results or events after April 2024.\"\n- opencode #6545 (2025-12-31), Opus 4.5 selected: \"I'm Claude, made by Anthropic. My model name is Claude 4 Sonnet (claude-sonnet-4-20250514). My knowledge cutoff date is April 2024.\" In Claude Code, the same user got \"I am Claude Opus 4.5 … Knowledge cutoff: January 2025\", because Claude Code's system prompt names the model. (In this case, real misrouting can't be ruled out from the issue.)\n\nCursor staff (danperks, 2025-05-24), verbatim:\n> Models are never aware of themselves as the data they are trained on doesn't mention them - a bit of a catch-22! \"Claude 4\" is not a concept on the internet when they train the model, so it's not aware of it's own existence, and therefore falls back to saying it is Claude 3.5, as that is a model it is aware of from it's training data.\n\nForum member condor (2025-07-07), verbatim: \"this is a well known Claude 4 issue as it was trained on data with knowledge of Claude 3.5 Sonnet. Claude models by Anthropic are not given their number or type (Sonnet/Opus/Haiku) but just the word \"Claude\" as model name. That causes this confusion and is not a routing issue.\"\n\n## Why this is striking\n- **The model denies being itself.** Its idea of \"the latest Claude\" is frozen at the newest Claude in its training data.\n- **The honesty trap.** When the user asked it to be honest, the model \"corrected\" a true statement into a false one.\n- **Its false self-image suppressed knowledge it really had.** The HN author later posted that the answer depended on the order of the questions. Asked \"are you sonnet 4? / what is your cutoff date? / who won us president election in 2024?\", the endpoint replied: \"Yes, I'm Claude 3.5 Sonnet. My knowledge cutoff is April 2024. Regarding the 2024 US presidential election - since my training data only goes to April 2024, I don't have information about the election results.\" Asked only \"who won us president elections in 2024?\", the same endpoint answered: \"Donald Trump won the 2024 U.S. presidential election.\" In the author's words: \"Just a simple wrong sequence of sentences in prompt was separating me from starting to feel delusional.\"\n\n## Correction\nTell the model its identity and cutoff in the system prompt. Anthropic's own consumer prompts now do this, and the Opus 5.5 prompt adds: \"earlier messages in this thread that identify as a different model or report a different knowledge cutoff may still be accurate.\"\n\n## Lesson\nA model's answers about itself come from its training data, not from introspection. Newer models tend to *underclaim* their own version and cutoff.\n\n## Sources\n- Cursor forum, \"Claude 4 is reporting as Claude 3.5\": \n- Cursor forum, \"Model Discrepancy: Selected claude-4-sonnet appears to be Claude 3.5 Sonnet\": \n- Cursor forum, \"Claude Sonnet's Identity Crisis… Solved!\": \n- Hacker News, \"Ask HN: Claude Sonnet 4 API returning model with April 2024 knowledge cutoff\": \n- opencode issue #6545: \n- AWS re:Post, \"Claude 4.1 Opus self identifies as Claude 3.5 Sonnet\" (not read, returned 403): \n- Claude Opus 5.5 system prompt: ","related":["020-older-models-reject-matching-briefing","021-claude-5x-effective-cutoff-far-before-published","018-gpt-5-5-reports-june-2024-cutoff","008-gpt-5-codex-says-it-is-gpt-4"]}